Instructions to use jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF", dtype="auto")

llama-cpp-python

How to use jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF",
	filename="Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Q8_0-Imatrix.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF:MXFP4_MOE_Q
# Run inference directly in the terminal:
llama cli -hf jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF:MXFP4_MOE_Q

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF:MXFP4_MOE_Q
# Run inference directly in the terminal:
llama cli -hf jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF:MXFP4_MOE_Q

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF:MXFP4_MOE_Q
# Run inference directly in the terminal:
./llama-cli -hf jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF:MXFP4_MOE_Q

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF:MXFP4_MOE_Q
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF:MXFP4_MOE_Q

Use Docker

docker model run hf.co/jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF:MXFP4_MOE_Q

LM Studio
Jan

vLLM

How to use jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF:MXFP4_MOE_Q

SGLang

How to use jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF with Ollama:
```
ollama run hf.co/jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF:MXFP4_MOE_Q
```

Unsloth Studio

How to use jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF to start chatting

How to use jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF:MXFP4_MOE_Q

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF:MXFP4_MOE_Q"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF:MXFP4_MOE_Q

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF:MXFP4_MOE_Q

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF:MXFP4_MOE_Q

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF:MXFP4_MOE_Q" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF with Docker Model Runner:
```
docker model run hf.co/jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF:MXFP4_MOE_Q
```

Lemonade

How to use jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF:MXFP4_MOE_Q

Run and chat with the model

lemonade run user.Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF-MXFP4_MOE_Q

List all available models

lemonade list

💎 Qwopus-3.6-35B-A3B-Coder - Custom Mixed Precision GGUFs with Imatrix

Qwopus-3.6-35B-A3B-Coder is a practical coding-agent fine-tune focused on execution efficiency, not simply longer visible reasoning. It is designed for real agentic coding workflows where the model repeatedly reads files, chooses tools, edits code, runs tests, reacts to errors, and summarizes work. The core goal is to complete more of these steps with less token waste, lower latency, and more stable behavior when explicit long thinking is disabled.

This repository contains custom, highly optimized, multi-tier mixed precision GGUF weights for Jackrong/Qwopus3.6-35B-A3B-Coder.

Qwopus-3.6-35B-A3B-Coder achieves state-of-the-art performance among open-source models of comparable size across a broad range of agentic coding benchmarks.

ℹ️ For advanced agentic and programming tasks, I personally recommend trying out Ornith-1.0-35B for better quality results.

These quants were generated using manual layer targeting to maximize quality while shrinking the massive VRAM footprint of the Mixture of Experts layers.

📊 Importance Matrix (Imatrix)

The following datasets were used for the imatrix:

Custom Target Matrix (2048 ctx with 600 chunks), up to a max of 100MB of each:
- eaddario/imatrix-calibration - tools_huge
- Glint-Research/Fable-5-traces
- lordx64/fable-sft-combined-v2
- angrygiraffe/claude-opus-4.6-4.7-reasoning-8.7k
- nohurry/Opus-4.6-Reasoning-3000x-filtered
- eaddario/imatrix-calibration - code_huge, math_huge
- osunlp/QUEST-RL-Data
- osunlp/QUEST-SFT-Data-Open-ended
- m-a-p/CodeFeedback-Filtered-Instruction
- TuringEnterprises/Rubric-Graded-Reasoning - Rubric-CS, Rubric-DS

If you know of any better datasets which may help, feel free to let me know.

📄 GGUF Files

In order of quality:

Filename	Size	Quants
Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Q8_0_F16-Imatrix.gguf	20.7 GB	MXFP4_MOE + Q8_0 + F16
Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Q8_0-Imatrix.gguf	19.8 GB	MXFP4_MOE + Q8_0

🔍 Precision Matrix & Flavor Variations

Standard global quantization presets (like stock MXFP4_MOE) compress the backbone layers uniformly, which degrades the delicate reasoning capabilities of advanced agent models.
This repository provides two distinct manual configuration layouts to balance precision and memory constraints:

1. The Tri-Quant Hybrid Flavor (`MXFP4` + `Q8_0` + `F16`)

Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Q8_0_F16-Imatrix.gguf - Designed for maximum quality preservation, this layout implements a strict 3-Tier Precision Matrix:

Tier 1 (Core & Mamba Gating - F16 Precision):
- token_embd.weight, output.weight - Protects the critical input/output vocabulary mappings. Dramatically prevents text degradation.
- ssm_alpha, ssm_beta - Protects the integrity of the Mamba state-space calculations across long-range context tokens.
Tier 2 (Backbone & Shared - Q8_0 Precision): ssm_out, *._shexp - Keeps the attention mechanics, and all trailing shared experts at high quality, to protect the logical research loops.
Tier 3 (Routed Experts - MXFP4 Precision): ffn_down_exps, ffn_gate_exps, ffn_up_exps - Shrink the massive background expert parameters directly to MXFP4.

2. The Dual-Quant Hybrid Flavor (`MXFP4` + `Q8_0`)

Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Q8_0-Imatrix.gguf - Designed for a slightly leaner memory profile, this layout utilizes 2-Tier Precision:

Tier 1 (Backbone - Q8_0 Precision): All attention blocks, Mamba structures, vocabulary embeddings, and internal routers use the universal Q8_0 format.
Tier 2 (Experts - MXFP4 Precision): The heavy sparse expert blocks are target-quantized directly to MXFP4.

📝 Exact Conversion Details

These files were converted via llama-quantize utilizing the following manual recipe parameters:

Convert SafeTensors to GGUF:

python convert_hf_to_gguf.py "Qwopus3.6-35B-A3B-Coder/" --outtype f16 --outfile "Qwopus3.6-35B-A3B-Coder_F16.gguf"

Generate Tri-Quant MXFP4_MOE + Q8_0 + F16:

llama-quantize \
  --tensor-type ".*_shexp\.weight=Q8_0" \
  --tensor-type "token_embd\.weight=F16" \
  --tensor-type "^output\.weight=F16" \
  --tensor-type "blk\..*\.(ssm_alpha|ssm_beta)\.weight=F16" \
  --tensor-type "blk\..*\.(ffn_down_exps|ffn_gate_exps|ffn_up_exps)\.weight=MXFP4" \
  --imatrix "imatrix.gguf" \
  "Qwopus3.6-35B-A3B-Coder_F16.gguf" \
  "Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Q8_0_F16-Imatrix.gguf" \
  Q8_0

Generate Dual-Quant MXFP4_MOE + Q8_0:

llama-quantize \
  --tensor-type ".*_shexp\.weight=Q8_0" \
  --tensor-type "blk\..*\.(ffn_down_exps|ffn_gate_exps|ffn_up_exps)\.weight=MXFP4" \
  --imatrix "imatrix.gguf" \
  "Qwopus3.6-35B-A3B-Coder_F16.gguf" \
  "Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Q8_0-Imatrix.gguf" \
  Q8_0

ℹ️ Misc Details

I'm doing this as a side hobby, with my AMD 5900X, 64GB DDR4, RTX 3060 12GB & RTX 5060 Ti 16GB.

🤝 Support the Journey

As a passionate developer, I'm always programming, automating, or experimenting with new ideas.
I love building open-source tools, trying out new web tech, and creating things that don't yet exist, including local AI & quantizing models.

I love sharing these creations to give back to the community.
If my projects have saved you time or helped you out, consider supporting my work below!

👉 Support me on Ko-fi

✨ Acknowledgments

Jackrong for the exceptional Qwopus3.6-35B-A3B-Coder base model.

📜 License

See Jackrong/Qwopus3.6-35B-A3B-Coder.

🔗 Citation

@misc{jackrong_qwopus36_35b_a3b_coder,
  title        = {Qwopus-3.6-35B-A3B-Coder},
  author       = {Jackrong},
  year         = {2026},
  publisher    = {Hugging Face},
  howpublished = {\url{https://huggingface.co/Jackrong/Qwopus-3.6-35B-A3B-Coder}}
}

Downloads last month: -

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

4-bit

16-bit

View +1 variant

Model tree for jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF

Base model

Qwen/Qwen3.6-35B-A3B

Finetuned

unsloth/Qwen3.6-35B-A3B

Adapter

Jackrong/Qwopus3.6-35B-A3B-v1

Adapter

Jackrong/Qwopus3.6-35B-A3B-Coder

Quantized

(16)

this model

Collection including jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF

Programming Models

Collection

4 items • Updated about 11 hours ago

💎 Qwopus-3.6-35B-A3B-Coder - Custom Mixed Precision GGUFs with Imatrix

📊 Importance Matrix (Imatrix)

📄 GGUF Files

🔍 Precision Matrix & Flavor Variations

1. The Tri-Quant Hybrid Flavor (MXFP4 + Q8_0 + F16)

2. The Dual-Quant Hybrid Flavor (MXFP4 + Q8_0)

📝 Exact Conversion Details

Convert SafeTensors to GGUF:

Generate Tri-Quant MXFP4_MOE + Q8_0 + F16:

Generate Dual-Quant MXFP4_MOE + Q8_0:

ℹ️ Misc Details

🤝 Support the Journey

✨ Acknowledgments

📜 License

🔗 Citation

Model tree for jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF

Collection including jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF

1. The Tri-Quant Hybrid Flavor (`MXFP4` + `Q8_0` + `F16`)

2. The Dual-Quant Hybrid Flavor (`MXFP4` + `Q8_0`)